End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: microsoft/phi-2
|
| 3 |
+
datasets:
|
| 4 |
+
- generator
|
| 5 |
+
library_name: peft
|
| 6 |
+
license: mit
|
| 7 |
+
tags:
|
| 8 |
+
- trl
|
| 9 |
+
- sft
|
| 10 |
+
- generated_from_trainer
|
| 11 |
+
model-index:
|
| 12 |
+
- name: phi-2-sft-openhermes-128k-v2
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# phi-2-sft-openhermes-128k-v2
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the generator dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- eval_loss: 1.0751
|
| 24 |
+
- eval_model_preparation_time: 0.0286
|
| 25 |
+
- eval_runtime: 21.3878
|
| 26 |
+
- eval_samples_per_second: 18.375
|
| 27 |
+
- eval_steps_per_second: 4.629
|
| 28 |
+
- epoch: 1.2974
|
| 29 |
+
- step: 3209
|
| 30 |
+
|
| 31 |
+
## Model description
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Intended uses & limitations
|
| 36 |
+
|
| 37 |
+
More information needed
|
| 38 |
+
|
| 39 |
+
## Training and evaluation data
|
| 40 |
+
|
| 41 |
+
More information needed
|
| 42 |
+
|
| 43 |
+
## Training procedure
|
| 44 |
+
|
| 45 |
+
### Training hyperparameters
|
| 46 |
+
|
| 47 |
+
The following hyperparameters were used during training:
|
| 48 |
+
- learning_rate: 4e-05
|
| 49 |
+
- train_batch_size: 4
|
| 50 |
+
- eval_batch_size: 4
|
| 51 |
+
- seed: 42
|
| 52 |
+
- gradient_accumulation_steps: 4
|
| 53 |
+
- total_train_batch_size: 16
|
| 54 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 55 |
+
- lr_scheduler_type: linear
|
| 56 |
+
- lr_scheduler_warmup_steps: 400
|
| 57 |
+
- num_epochs: 2
|
| 58 |
+
- mixed_precision_training: Native AMP
|
| 59 |
+
|
| 60 |
+
### Framework versions
|
| 61 |
+
|
| 62 |
+
- PEFT 0.12.0
|
| 63 |
+
- Transformers 4.44.0
|
| 64 |
+
- Pytorch 2.4.0+cu121
|
| 65 |
+
- Datasets 2.20.0
|
| 66 |
+
- Tokenizers 0.19.1
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 355426922
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9bb0e087fa83dffaed31cd3c60aef5330bea3936d2f26423ebd2deba4e601e59
|
| 3 |
size 355426922
|
runs/Aug07_01-24-31_ab5e355bc8ee/events.out.tfevents.1722993895.ab5e355bc8ee.6371.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b64e8ea52de111f7614bed61af2017a6657301a7b457de223004eb5e99d9668
|
| 3 |
+
size 14717
|